arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 1902.06015stat.MLcond-mat.stat-mechcs.LGmath.STstat.TH
收藏

双层神经网络的平均场理论:无量纲界与核极限

Mean-field theory of two-layers neural networks: dimension-free bounds and kernel limit

Stanford University(斯坦福大学)

Song Mei, Theodor Misiakiewicz, Andrea Montanari

摘要:

我们考虑使用随机梯度下降来学习两层神经网络。该学习动态的平均场描述通过$R^D$中的概率分布的空间中的演变来近似网络权重的演变(其中$D$是与每个神经元相关联的参数的数量)。这种演化可以通过偏微分方程来定义,或者等价地定义为概率分布的Wasserstein空间中的梯度流。早期的工作表明,(在一些规律性的假设下),平均场的描述是准确的,只要隐藏单元的数量远远大于尺寸$D$。在本文中,我们建立更强和更一般的近似保证。首先,我们证明了隐藏单元的数量只需要大于一个依赖于数据的正则性的数量,并且与维度无关。接下来,我们将这种分析推广到无界激活函数的情况,这是不包括在早期的界限。我们将我们的结果扩展到有噪随机梯度下降。最后,我们证明了核岭回归可以作为均值场分析的一个特殊极限来恢复。

英文摘要:

We consider learning two layer neural networks using stochastic gradient descent. The mean-field description of this learning dynamics approximates the evolution of the network weights by an evolution in the space of probability distributions in $R^D$ (where $D$ is the number of parameters associated to each neuron). This evolution can be defined through a partial differential equation or, equivalently, as the gradient flow in the Wasserstein space of probability distributions. Earlier work shows that (under some regularity assumptions), the mean field description is accurate as soon as the number of hidden units is much larger than the dimension $D$. In this paper we establish stronger and more general approximation guarantees. First of all, we show that the number of hidden units only needs to be larger than a quantity dependent on the regularity properties of the data, and independent of the dimensions. Next, we generalize this analysis to the case of unbounded activation functions, which was not covered by earlier bounds. We extend our results to noisy stochastic gradient descent. Finally, we show that kernel ridge regression can be recovered as a special limit of the mean field analysis.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑